Trace
Back to Trace

Press

Press kit

Boilerplate, logos, and contact for writers, reviewers, and podcast hosts covering Trace.

Last updated
7 October 2026
Contact
[email protected]

At a glance

  • What it is: a native macOS menu-bar app that records meetings and transcribes them on-device.
  • Hero claim: meeting summaries that never leave your Mac. No meeting bots, no accounts, no cloud.
  • Three things that set it apart: it's local (on-device, nothing leaves your Mac), it's fast (Apple-silicon-optimised and on-device, so no upload and no queue), and it has key moments (flag decisions mid-call with one keystroke, inline in the transcript).
  • How you use it: one keystroke to start, one to flag a key moment, one to stop. Out comes a markdown transcript.
  • Price: one-time, no subscription. Direct from us it is tiered by how many Macs you need, from £29. On the Mac App Store and Setapp it is a flat £39.
  • Availability: macOS 14+ on Apple silicon.
  • Get it: Trace on the Mac App Store, or direct from traceapp.info with a seven-day trial.

Reception

Trace launched with a Show HN that reached the Hacker News front page at around 200 points. On the Mac App Store it reached #3 on Top Paid, behind Shadowrocket and Logic Pro, and sold hundreds of copies in its first days.

Short boilerplate

Trace is a native macOS menu-bar app for meeting capture and transcription. It records mic and system audio with one keystroke, transcribes on-device using a local speech model, and identifies each speaker on the call so every line carries its own label, numbered to start and renameable after the meeting. Flag key moments live with ⌘⇧K and they sit inline in the markdown transcript at the exact timestamp they happened. The resulting transcript is plain markdown, ready to paste into Notion, Obsidian, or any AI notetaker. Trace hands you that raw, contextual text to take wherever you like, and it can also write a summary for you on-device with one tap, using its own local model. Your audio never leaves the Mac either way, and there are no meeting bots, no accounts, and no telemetry. The only required network request is a one-time download of the speech and speaker models on first run. An optional calendar connection can name sessions after the meeting you are in, reading the Mac's calendar entirely on-device (covering any account) or connecting to Google directly. It is opt-in, read-only, and off by default.

Long boilerplate

Trace is a Mac menu-bar app for on-device meeting transcription with three design pillars: everything is local, transcription is fast, and the user can flag key moments live. It records the microphone and any audio playing through the Mac (Zoom, Teams, Google Meet, Slack, a phone on speaker) as two separate tracks, transcribes them locally using an on-device speech model, and writes a clean markdown transcript with speaker labels and timestamps. Mic-track lines carry your editable label (Microphone by default); system-audio lines run through an on-device speaker identifier so each distinct voice on the call gets its own numbered label (Speaker 1, Speaker 2, and so on). After the call you can put real names to those voices, merging any the model split apart, and Trace remembers a named voice the next time it hears them. All processing stays on the Mac.

The interaction that sets Trace apart is the key moment: hit ⌘⇧K mid-call, type a short note, hit Enter. The flag sits inline in the transcript as a gold blockquote at the exact timestamp you pressed it. You stay in the conversation, and the record you hand off afterwards has explicit, human-authored signposts for the moments that actually mattered. Key moments travel with the transcript into whatever AI notetaker you paste it into (ChatGPT, Claude, the notetaker of your choice), so any summary is anchored to what the human in the room said was important. Trace can also write that summary itself, on-device with one tap using its own local model, always folding in the moments you starred. Either way the transcript stays plain and portable, and nothing leaves the Mac.

Recordings stay on-device. The only required network request is a one-time download of the chosen speech model plus its speaker-identification models (roughly 220 MB to 950 MB depending on the model) from Hugging Face on first use. After that, recording, transcription, and speaker identification never touch the network, and there are no accounts and no telemetry anywhere in the app. The direct download adds two small requests of its own, a licence check and an update check against Trace's own server, and neither one carries audio or transcripts. Sessions live inside Trace's sandboxed container under ~/Library/Containers/ by default, browseable in Finder and deletable any time, and can be pointed at any folder you choose instead. You can also pause mid-recording with ⌘⇧P, rename past sessions from the menu bar, and enable Stealth Mode to hide the floating pill and silence every sound the app plays. Trace runs on macOS 14.4 and later on Apple silicon and is a one-time purchase with no subscription, from £29 buying direct (where the licence is tiered by how many Macs you need) or a flat £39 on the Mac App Store and Setapp. It ships three ways: a sandboxed app on the Mac App Store, a direct download from traceapp.info with a seven-day trial, and on Setapp.

An optional calendar connection is available for users who want recordings to auto-name after the meeting they're in. There are two sources, chosen in Preferences. Mac Calendar reads upcoming events on-device through Apple's EventKit, covering every account already set up in the Calendar app (iCloud, Google, Exchange, and others) with no sign-in and no network request at all. Google Calendar connects one account directly using the read-only calendar scope and never writes back. With either source, a small pill appears one minute before each meeting offering to start recording. The calendar connection is off by default and changeable at any time from Preferences; Google is the only source that sends a network request after the model download, while Mac Calendar stays entirely on-device. No other integrations, and no plans for any that would route audio or transcripts off the Mac.

Features, one-liners

The three pillars:

  • Yours, locally: plain audio and markdown files on your disk. No cloud service, no accounts, no telemetry. Transcription runs entirely on-device.
  • Fast and local: a local speech model transcribes on your Mac's Apple silicon. No upload, no queue.
  • Flag key moments live: hit ⌘⇧K mid-meeting to mark a decision with an optional note. The flag sits inline in the transcript at the exact timestamp.

And the supporting interactions:

  • Summarise on-device (optional): one tap turns the transcript into a summary written next to it, generated by Trace's own on-device model. The key moments you flagged are always included, and nothing leaves the Mac.
  • Out of the way until you need it: one keystroke summons Trace over any app; another dismisses it.
  • Markdown you can paste anywhere: Notion, Obsidian, ChatGPT, Claude, any AI notetaker, or plain text.
  • Every transcript, one click away: the menu bar keeps a quiet list of your sessions, each one one click from copy or reveal-in-Finder.
  • Speaker-aware, with names: each distinct voice gets its own label, numbered to start and renameable after the call, with the names carried across future recordings. Speaker identification runs on-device alongside transcription.
  • Multilingual: the speech models auto-detect the spoken language; the accurate default covers around 99 languages.
  • Drive it from Shortcuts and Spotlight: start, stop, pause, capture a key moment, or grab the last transcript or summary, and optionally run a Shortcut automatically when a transcription finishes.
  • Command line: an optional tracecli tool reads past sessions off disk and controls the app through a trace:// URL scheme.
  • Back-to-back recording: stop one meeting and start the next straight away while the previous one transcribes in the background.
  • Meeting-aware (optional): connect your calendar (Mac Calendar on-device, or Google) and Trace names sessions after the meeting you're in and nudges you one minute before each one starts. Read-only, opt-in, off by default.

Facts for fact-checking

  • Speech models: three on-device options. Whisper large-v3-turbo is the accurate default; Parakeet TDT v3 is the balanced middle option; a small Parakeet model is the fastest. Each downloads its weights the first time you use it.
  • Languages: the models auto-detect the spoken language. Whisper (the default) covers roughly 99 languages; Parakeet TDT v3 covers 25 European languages; the smallest model is English-only.
  • Speaker identification: on-device diarisation models. The default Whisper engine uses SpeakerKit's Pyannote pipeline; the Parakeet models use FluidAudio's diariser.
  • Speaker naming: the numbered labels can be renamed and merged after a call and are saved alongside the transcript. Names are remembered across calls through an on-device voice registry, with a People list in Preferences to manage them. The underlying numbered transcript is never overwritten.
  • Model runtimes: the WhisperKit and FluidAudio Swift packages, running on-device (no Python, no subprocess).
  • Audio capture: AVAudioEngine for mic, Core Audio process taps for system audio. Tracks are written as 16 kHz mono float32 WAV files.
  • Hotkeys: Carbon RegisterEventHotKey (Mac App Store safe, does not require Accessibility permission), user-remappable.
  • Default shortcuts: ⌘⇧R toggle recording, ⌘⇧K flag a key moment, ⌘⇧P pause or resume, ⌘⇧H show or hide the floating pill, ⌘⇧? reveal the recap of the last few minutes. Any shortcut can also be cleared to disable its hotkey.
  • Summaries: an optional Summarise action turns a transcript into a summary.md next to it, using Trace's own on-device language model (downloaded once, run locally through MLX). It always includes the key moments you flagged and runs entirely on-device.
  • Automation: Trace exposes App Intents (Start, Stop, Pause, Resume, Mute, Capture key moment, Get last transcript, Get last summary, Summarise last meeting) to Apple's Shortcuts app and Spotlight, and can run a Shortcut of your choice when a transcription finishes.
  • Command line: an optional tracecli tool, installed via Homebrew, reads past sessions off disk and controls the running app through a trace:// URL scheme. It is not bundled in the App Store build.
  • Audio retention: the raw mic and system WAV files can be kept, deleted as soon as the transcript is ready, or cleared after a window you set. By default only the audio goes; the timed sweep can be set to clear the whole recording instead.
  • Distribution: Mac App Store (sandboxed, hardened runtime), direct download from traceapp.info, and Setapp.
  • Dependencies: Swift and Apple frameworks, plus FluidAudio for the on-device speech runtime. The only required network traffic is a one-time model weight download from Hugging Face on first run.
  • Optional calendar sources: Mac Calendar via EventKit (on-device, no network, covers any account in the Calendar app) or Google Calendar (read-only, OAuth with PKCE). Off by default. Used for session auto-naming and a one-minute pre-meeting pill nudge. Changeable from Preferences.

Downloads

Brand colours are graphite #14161F and ivory #F4E4CC. Please give the mark at least one bar's width of clear space, and don't recolour it, rotate or skew it, or set it on a busy background.

Contact

[email protected]